Clinical Research Institute, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea.
Comput Methods Programs Biomed. 2020 Mar;185:105150. doi: 10.1016/j.cmpb.2019.105150. Epub 2019 Oct 22.
Cardiac perfusion magnetic resonance imaging (MRI) with first pass dynamic contrast enhancement (DCE) is a useful tool to identify perfusion defects in myocardial tissues. Automatic segmentation of the myocardium can lead to efficient quantification of perfusion defects. The purpose of this study was to investigate the usefulness of uncertainty estimation in deep convolutional neural networks for automatic myocardial segmentation.
A U-Net segmentation model was trained on the cardiac cine data. Monte Carlo dropout sampling of the U-Net model was performed on the dynamic perfusion datasets frame-by-frame to estimate the standard deviation (SD) maps. The uncertainty estimate based on the sum of the SD values was used to select the optimal frames for endocardial and epicardial segmentations. DCE perfusion data from 35 subjects (14 subjects with coronary artery disease, 8 subjects with hypertrophic cardiomyopathy, and 13 healthy volunteers) were evaluated. The Dice similarity scores of the proposed method were compared with those of a semi-automatic U-Net segmentation method, which involved user selection of an image frame for segmentation in the cardiac perfusion dataset.
The proposed method was fully automatic and did not require manual labeling of the cardiac perfusion image data for model development. The mean Dice similarity score of the proposed automatic method was 0.806 (±0.096), which was comparable to the 0.808 (±0.084) Dice score of the semi-automatic U-Net segmentation method (intraclass correlation coefficient = 0.61, P < 0.001).
Our study demonstrated the feasibility of applying an existing model trained on cardiac cine data to dynamic cardiac perfusion data to achieve robust and automatic segmentation of the myocardium. The uncertainty estimates can be used for screening purposes, which would facilitate the cases with high endocardial and epicardial uncertainty estimates to be sent for further evaluation and correction by human experts.
首过动态对比增强（DCE）心脏灌注磁共振成像是一种识别心肌组织灌注缺陷的有用工具。心肌的自动分割可以实现灌注缺陷的高效量化。本研究旨在探讨不确定性估计在用于自动心肌分割的深度卷积神经网络中的有用性。
在心脏电影数据上训练 U-Net 分割模型。对动态灌注数据集逐帧进行蒙特卡罗 dropout 采样，以估计标准偏差（SD）图。基于 SD 值之和的不确定性估计用于选择心内膜和心外膜分割的最佳帧。评估了 35 名受试者（14 名冠心病患者、8 名肥厚型心肌病患者和 13 名健康志愿者）的 DCE 灌注数据。比较了所提出方法的 Dice 相似性评分与半自动 U-Net 分割方法的评分，半自动 U-Net 分割方法涉及在心脏灌注数据集用户选择用于分割的图像帧。
所提出的方法是全自动的，不需要手动标记心脏灌注图像数据来开发模型。所提出的自动方法的平均 Dice 相似性评分（SD）为 0.806（±0.096），与半自动 U-Net 分割方法的 0.808（±0.084）Dice 评分相当（组内相关系数=0.61，P<0.001）。
我们的研究证明了将在心脏电影数据上训练的现有模型应用于动态心脏灌注数据以实现稳健且自动的心肌分割的可行性。不确定性估计可用于筛选目的，这将有助于那些具有高内心和心外膜不确定性估计的病例由人类专家进行进一步评估和修正。
